Bluecat: A local uncertainty estimator for deterministic simulations and predictions

D. Koutsoyiannis, and A. Montanari, Bluecat: A local uncertainty estimator for deterministic simulations and predictions, Water Resources Research, 58 (1), e2021WR031215, doi:10.1029/2021WR031215, 2022.

[doc_id=2166]

[English]

We present a new method for simulating and predicting hydrologic variables with uncertainty assessment and provide example applications to river flows. The method is identified with the acronym "Bluecat" and is based on the use of a deterministic model which is subsequently converted to a stochastic formulation. The latter provides an adjustment on statistical basis of the deterministic prediction along with its confidence limits. The distinguishing features of the proposed approach are the ability to infer the probability distribution of the prediction without requiring strong hypotheses on the statistical characterization of the prediction error (e.g. normality, homoscedasticity) and its transparent and intuitive use of the observations. Bluecat makes use of a rigorous theory to estimate the probability distribution of the predictand conditioned by the deterministic model output, by inferring the conditional statistics of observations. Therefore, Bluecat bridges the gaps between deterministic (possibly physically-based, or deep learning-based) and stochastic models as well as between rigorous theory and transparent use of data with an innovative and user-oriented approach. We present two examples of application to the case studies of the Arno River at Subbiano and Sieve River at Fornacina. The results confirm the distinguishing features of the method along with its technical soundness. We provide an open software working in the R environment, along with help facilities and detailed instructions to reproduce the case studies presented here.

PDF Full text (1850 KB)

PDF Additional material:

Remarks:

The R code used in this paper can be downloaded from https://github.com/albertomontanari/hymodbluecat

Our works referenced by this work:

1. A. Montanari, and D. Koutsoyiannis, A blueprint for process-based modeling of uncertain hydrological systems, Water Resources Research, 48, W09555, doi:10.1029/2011WR011412, 2012.
2. A. Montanari, and D. Koutsoyiannis, Reply to comment by G. Nearing on ‘‘A blueprint for process-based modeling of uncertain hydrological systems’’, Water Resources Research, 50 (7), 6264–6268, doi:10.1002/2013WR014987, 2014.
3. A. Montanari, and D. Koutsoyiannis, Modeling and mitigating natural hazards: Stationarity is immortal!, Water Resources Research, 50 (12), 9748–9756, doi:10.1002/2014WR016092, 2014.
4. A. Sikorska, A. Montanari, and D. Koutsoyiannis, Estimating the uncertainty of hydrological predictions through data-driven resampling techniques, Journal of Hydrologic Engineering (ASCE), 20 (1), doi:10.1061/(ASCE)HE.1943-5584.0000926, 2015.
5. D. Koutsoyiannis, and A. Montanari, Negligent killing of scientific concepts: the stationarity case, Hydrological Sciences Journal, 60 (7-8), 1174–1183, doi:10.1080/02626667.2014.959959, 2015.
6. G. Papacharalampous, H. Tyralis, and D. Koutsoyiannis, Comparison of stochastic and machine learning methods for multi-step ahead forecasting of hydrological processes, Stochastic Environmental Research & Risk Assessment, doi:10.1007/s00477-018-1638-6, 2019.
7. D. Koutsoyiannis, Knowable moments for high-order stochastic characterization and modelling of hydrological processes, Hydrological Sciences Journal, 64 (1), 19–33, doi:10.1080/02626667.2018.1556794, 2019.
8. G. Papacharalampous, H. Tyralis, A. Langousis, A. W. Jayawardena, B. Sivakumar, N. Mamassis, A. Montanari, and D. Koutsoyiannis, Large-scale comparison of machine learning regression algorithms for probabilistic hydrological modelling via post-processing of point predictions, European Geosciences Union General Assembly 2019, Geophysical Research Abstracts, Vol. 21, Vienna, EGU2019-3576, European Geosciences Union, 2019.
9. G. Papacharalampous, H. Tyralis, A. Langousis, A. W. Jayawardena, B. Sivakumar, N. Mamassis, A. Montanari, and D. Koutsoyiannis, Probabilistic hydrological post-processing at scale: Why and how to apply machine-learning quantile regression algorithms, Water, doi:10.3390/w11102126, 2019.
10. G. Papacharalampous, H. Tyralis, D. Koutsoyiannis, and A. Montanari, Quantification of predictive uncertainty in hydrological modelling by harnessing the wisdom of the crowd: A large-sample experiment at monthly timescale, Advances in Water Resources, 136, 103470, doi:10.1016/j.advwatres.2019.103470, 2020.
11. D. Koutsoyiannis, and A. Montanari, A brisk local uncertainty estimator for hydrologic simulations and predictions (Blue Cat), European Geosciences Union General Assembly 2020, Geophysical Research Abstracts, Vol. 22, Vienna, doi:10.5194/egusphere-egu2020-10125, 2020.
12. D. Koutsoyiannis, Stochastics of Hydroclimatic Extremes - A Cool Look at Risk, Edition 3, ISBN: 978-618-85370-0-2, 391 pages, doi:10.57713/kallipos-1, Kallipos Open Academic Editions, Athens, 2023.

Our works that reference this work:

1. D. Koutsoyiannis, An open letter to the Editor of Frontiers, doi:10.13140/RG.2.2.34248.39689/1, December 2021.
2. D. Koutsoyiannis, and A. Montanari, Climate extrapolations in hydrology: The expanded Bluecat methodology, Hydrology, 9, 86, doi:10.3390/hydrology9050086, 2022.
3. D. Koutsoyiannis, C. Onof, A. Christofides, and Z. W. Kundzewicz, Revisiting causality using stochastics: 2. Applications, Proceedings of The Royal Society A, 478 (2261), 20210836, doi:10.1098/rspa.2021.0836, 2022.
4. E. Rozos, D. Koutsoyiannis, and A. Montanari, KNN vs. Bluecat — Machine Learning vs. Classical Statistics, Hydrology, 9, 101, doi:10.3390/hydrology9060101, 2022.
5. D. Koutsoyiannis, and C. Vournas, Revisiting the greenhouse effect—a hydrological perspective, Hydrological Sciences Journal, 69 (2), 151–164, doi:10.1080/02626667.2023.2287047, 2024.

Tagged under: Determinism vs. stochasticity, Hydrological models, Uncertainty